{"id":"https://openalex.org/W7161135412","doi":"https://doi.org/10.48550/arxiv.2605.12648","title":"Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise","display_name":"Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161135412","doi":"https://doi.org/10.48550/arxiv.2605.12648"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.12648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.12648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136152548","display_name":"Puyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Puyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019619325","display_name":"Jan Schuchardt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schuchardt, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124370048","display_name":"Nikita Kalinin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kalinin, Nikita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136100882","display_name":"Junyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Junyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108299659","display_name":"Sophie Fellenz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fellenz, Sophie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127845446","display_name":"Christoph Lampert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lampert, Christoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5099337782","display_name":"Marius Kloft","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kloft, Marius","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.894599974155426,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.894599974155426,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.03610000014305115,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0142000000923872,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6171000003814697},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5867999792098999},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5422999858856201},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5056999921798706},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4708999991416931},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6171000003814697},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5805000066757202},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5056999921798706},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4708999991416931},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3325999975204468},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.26589998602867126},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.12648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.12648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,146],"establish":[1],"the":[2,58,87,120,126,135,139,160,181,187,194],"first":[3,195],"population":[4,183,198],"risk":[5,184,199],"bounds":[6],"for":[7,61,95,115,205,213],"Kolmogorov-Arnold":[8],"Networks":[9],"(KANs)":[10],"trained":[11],"by":[12,55,97],"mini-batch":[13,56],"SGD":[14,20,26,132],"with":[15,28,175],"gradient":[16,67],"clipping,":[17],"covering":[18],"non-private":[19],"as":[21,23],"well":[22],"differentially":[24],"private":[25],"(DP-SGD)":[27],"Gaussian":[29],"perturbations":[30],"that":[31,158],"interpolate":[32],"between":[33],"independent":[34],"and":[35,70,91,134,164,197],"temporally":[36],"correlated":[37,144],"noise.":[38],"This":[39],"setting":[40],"is":[41,54,110,193],"substantially":[42],"closer":[43],"to":[44],"practice":[45],"than":[46,65,81],"prior":[47],"KAN":[48],"theory":[49],"along":[50],"two":[51],"axes:":[52],"training":[53,118,207],"SGD,":[57],"standard":[59,130],"recipe":[60],"modern":[62],"networks,":[63],"rather":[64],"full-batch":[66,89],"descent":[68],"(GD);":[69],"correlated-noise":[71,116,203],"mechanisms":[72],"have":[73],"empirically":[74],"shown":[75],"a":[76,111,155,165,176,202],"more":[77],"favorable":[78],"privacy-utility":[79],"tradeoff":[80],"independent-noise":[82,92],"mechanisms.":[83],"Our":[84],"results":[85,94],"cover":[86],"corresponding":[88],"GD":[90],"DP-GD":[93],"KANs":[96],"Wang":[98],"et":[99],"al.":[100],"(2026),":[101],"while":[102],"yielding":[103],"sharper":[104],"fixed-second-layer":[105],"specializations.":[106],"The":[107],"technical":[108],"core":[109],"new":[112],"analysis":[113,174,200],"route":[114],"DP":[117,206],"in":[119,211],"non-convex":[121],"regime.":[122],"Temporal":[123],"dependence":[124],"breaks":[125],"conditional-centering":[127],"structure":[128,142],"underlying":[129],"one-step":[131],"arguments,":[133],"projection":[136,169],"step":[137],"obstructs":[138],"exact":[140],"cancellation":[141],"of":[143,189,201],"perturbations.":[145],"address":[147],"these":[148],"difficulties":[149],"through":[150],"an":[151],"auxiliary":[152],"unprojected":[153],"dynamics,":[154],"shifted":[156],"iterate":[157],"absorbs":[159],"current":[161],"noise":[162],"perturbation,":[163],"high-probability":[166],"bootstrap":[167],"certifying":[168],"inactivity.":[170],"Combining":[171],"this":[172,192],"optimization":[173,196],"stability-based":[177],"generalization":[178],"argument":[179],"yields":[180],"stated":[182],"bounds.":[185],"To":[186],"best":[188],"our":[190],"knowledge,":[191],"mechanism":[204],"beyond":[208],"convex":[209],"learning,":[210],"particular":[212],"neural":[214],"networks.":[215]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}